gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[GH-PAGES] Updated website

Browse Source
This commit is contained in:
Philippe Tillet
2021-07-23 05:18:00 +00:00
parent 98967714bd
commit c0a449409d
19 changed files with 120 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py
View File

@@ -91,8 +91,9 @@ print(f'The maximum difference between torch and triton is ' f'{torch.max(torch.
x_vals=[2**i for i in range(12, 28, 1)], # different possible values for `x_name`
x_log=True, # x axis is logarithmic
line_arg='provider', # argument name whose value corresponds to a different line in the plot
line_vals=['torch', 'triton'], # possible values for `line_arg`
line_names=["Torch", "Triton"], # label name for the lines
line_vals=['triton', 'torch'], # possible values for `line_arg`
line_names=["Triton", "Torch"], # label name for the lines
styles=[('blue', '-'), ('green', '-')], # line styles
ylabel="GB/s", # label name for the y-axis
plot_name="vector-add-performance", # name for the plot. Used also as a file name for saving the plot.
args={} # values for function arguments not in `x_names` and `y_name`

BIN
_downloads/662999063954282841dc90b8945f85ce/tutorials_jupyter.zip
View File

Binary file not shown.

BIN
_downloads/763344228ae6bc253ed1a6cf586aa30d/tutorials_python.zip
View File

Binary file not shown.

2
_downloads/f191ee1e78dc52eb5f7cba88f71cef2f/01-vector-add.ipynb
View File

@@ -94,7 +94,7 @@
},
"outputs": [],
"source": [
"@triton.testing.perf_report(\n triton.testing.Benchmark(\n x_names=['size'], # argument names to use as an x-axis for the plot\n x_vals=[2**i for i in range(12, 28, 1)], # different possible values for `x_name`\n x_log=True, # x axis is logarithmic\n line_arg='provider', # argument name whose value corresponds to a different line in the plot\n line_vals=['torch', 'triton'], # possible values for `line_arg`\n line_names=[\"Torch\", \"Triton\"], # label name for the lines\n ylabel=\"GB/s\", # label name for the y-axis\n plot_name=\"vector-add-performance\", # name for the plot. Used also as a file name for saving the plot.\n args={} # values for function arguments not in `x_names` and `y_name`\n )\n)\ndef benchmark(size, provider):\n x = torch.rand(size, device='cuda', dtype=torch.float32)\n y = torch.rand(size, device='cuda', dtype=torch.float32)\n if provider == 'torch':\n ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)\n if provider == 'triton':\n ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))\n gbps = lambda ms: 12 * size / ms * 1e-6\n return gbps(ms), gbps(max_ms), gbps(min_ms)"
"@triton.testing.perf_report(\n triton.testing.Benchmark(\n x_names=['size'], # argument names to use as an x-axis for the plot\n x_vals=[2**i for i in range(12, 28, 1)], # different possible values for `x_name`\n x_log=True, # x axis is logarithmic\n line_arg='provider', # argument name whose value corresponds to a different line in the plot\n line_vals=['triton', 'torch'], # possible values for `line_arg`\n line_names=[\"Triton\", \"Torch\"], # label name for the lines\n styles=[('blue', '-'), ('green', '-')], # line styles\n ylabel=\"GB/s\", # label name for the y-axis\n plot_name=\"vector-add-performance\", # name for the plot. Used also as a file name for saving the plot.\n args={} # values for function arguments not in `x_names` and `y_name`\n )\n)\ndef benchmark(size, provider):\n x = torch.rand(size, device='cuda', dtype=torch.float32)\n y = torch.rand(size, device='cuda', dtype=torch.float32)\n if provider == 'torch':\n ms, min_ms, max_ms = triton.testing.do_bench(lambda: x + y)\n if provider == 'triton':\n ms, min_ms, max_ms = triton.testing.do_bench(lambda: add(x, y))\n gbps = lambda ms: 12 * size / ms * 1e-6\n return gbps(ms), gbps(max_ms), gbps(min_ms)"
]
},
{

BIN
_images/sphx_glr_01-vector-add_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 23 KiB

After

Width:  |  Height:  |  Size: 24 KiB

BIN
_images/sphx_glr_01-vector-add_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 15 KiB

After

Width:  |  Height:  |  Size: 15 KiB

BIN
_images/sphx_glr_02-fused-softmax_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 39 KiB

After

Width:  |  Height:  |  Size: 40 KiB

BIN
_images/sphx_glr_02-fused-softmax_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 24 KiB

After

Width:  |  Height:  |  Size: 24 KiB

BIN
_images/sphx_glr_03-matrix-multiplication_001.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 55 KiB

After

Width:  |  Height:  |  Size: 55 KiB

BIN
_images/sphx_glr_03-matrix-multiplication_thumb.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 32 KiB

After

Width:  |  Height:  |  Size: 32 KiB

25
_sources/getting-started/tutorials/01-vector-add.rst.txt
View File

@@ -153,7 +153,7 @@ We can now benchmark our custom op for vectors of increasing sizes to get a sens
To make things easier, Triton has a set of built-in utilities that allow us to concisely plot the performance of your custom ops
for different problem sizes.
.. GENERATED FROM PYTHON SOURCE LINES 86-112
.. GENERATED FROM PYTHON SOURCE LINES 86-113
.. code-block:: default
@@ -165,8 +165,9 @@ for different problem sizes.
x_vals=[2**i for i in range(12, 28, 1)], # different possible values for `x_name`
x_log=True, # x axis is logarithmic
line_arg='provider', # argument name whose value corresponds to a different line in the plot
line_vals=['torch', 'triton'], # possible values for `line_arg`
line_names=["Torch", "Triton"], # label name for the lines
line_vals=['triton', 'torch'], # possible values for `line_arg`
line_names=["Triton", "Torch"], # label name for the lines
styles=[('blue', '-'), ('green', '-')], # line styles
ylabel="GB/s", # label name for the y-axis
plot_name="vector-add-performance", # name for the plot. Used also as a file name for saving the plot.
args={} # values for function arguments not in `x_names` and `y_name`
@@ -190,12 +191,12 @@ for different problem sizes.
.. GENERATED FROM PYTHON SOURCE LINES 113-115
.. GENERATED FROM PYTHON SOURCE LINES 114-116
We can now run the decorated function above. Pass `show_plots=True` to see the plots and/or
`save_path='/path/to/results/' to save them to disk along with raw CSV data
.. GENERATED FROM PYTHON SOURCE LINES 115-115
.. GENERATED FROM PYTHON SOURCE LINES 116-116
.. code-block:: default
@@ -214,11 +215,11 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p
.. code-block:: none
vector-add-performance:
size Torch Triton
0 4096.0 9.600000 9.600000
size Triton Torch
0 4096.0 9.540372 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 76.800002 63.999998
2 16384.0 31.999999 31.999999
3 32768.0 63.999998 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
6 262144.0 341.333321 384.000001
@@ -229,8 +230,8 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
13 33554432.0 843.811163 843.811163
14 67108864.0 848.362445 849.278610
15 134217728.0 850.656574 851.577704
14 67108864.0 849.278610 848.362445
15 134217728.0 851.577704 850.656574
@@ -238,7 +239,7 @@ We can now run the decorated function above. Pass `show_plots=True` to see the p
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 0 minutes 11.005 seconds)
**Total running time of the script:** ( 0 minutes 10.999 seconds)
.. _sphx_glr_download_getting-started_tutorials_01-vector-add.py:

12
_sources/getting-started/tutorials/02-fused-softmax.rst.txt
View File

@@ -261,17 +261,17 @@ We will then compare its performance against (1) :code:`torch.softmax` and (2) t
softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 512.000001 546.133347 273.066674
1 384.0 585.142862 585.142862 267.130429
0 256.0 512.000001 546.133347 264.258068
1 384.0 585.142862 585.142862 261.446801
2 512.0 630.153853 606.814814 264.258068
3 640.0 682.666684 640.000002 269.473696
3 640.0 682.666684 640.000002 265.974036
4 768.0 702.171410 664.216187 273.066663
.. ... ... ... ...
93 12160.0 812.359066 405.755985 329.483481
93 12160.0 812.359066 406.179533 329.483481
94 12288.0 812.429770 415.661740 329.602681
95 12416.0 810.840807 412.149375 329.173158
96 12544.0 810.925276 412.971190 329.292871
97 12672.0 811.007961 412.097543 329.142870
97 12672.0 811.007961 412.097543 329.410251
[98 rows x 4 columns]
@@ -290,7 +290,7 @@ In the above plot, we can see that:
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 1 minutes 8.184 seconds)
**Total running time of the script:** ( 1 minutes 8.183 seconds)
.. _sphx_glr_download_getting-started_tutorials_02-fused-softmax.py:

70
_sources/getting-started/tutorials/03-matrix-multiplication.rst.txt
View File

@@ -369,39 +369,41 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
.. code-block:: none
matmul-performance:
M cuBLAS cuBLAS (+ torch.nn.LeakyReLU) Triton Triton (+ LeakyReLU)
0 128.0 0.455111 0.372364 0.512000 0.512000
1 256.0 2.978909 2.340571 3.276800 2.978909
2 384.0 7.372800 6.144000 8.507077 8.507077
3 512.0 14.563555 11.915636 16.384000 16.384000
4 640.0 22.260869 18.285714 23.272727 23.272727
5 768.0 32.768000 26.810182 34.028308 34.028308
6 896.0 39.025776 32.672744 39.025776 39.025776
7 1024.0 49.932191 41.943041 52.428801 52.428801
8 1152.0 44.566925 38.779015 46.656000 46.656000
9 1280.0 51.200001 44.521738 56.109587 56.109587
10 1408.0 64.138541 55.068446 65.684049 59.258433
11 1536.0 79.526831 67.408458 75.296679 75.296679
12 1664.0 63.372618 55.893862 61.636381 61.636381
13 1792.0 72.983276 63.860363 68.953520 68.953520
14 1920.0 66.782607 61.168141 68.776119 68.776119
15 2048.0 73.262953 65.793006 75.234154 75.234154
16 2176.0 82.473969 73.712993 79.540109 79.855747
17 2304.0 68.251065 62.207998 73.051599 73.051599
18 2432.0 71.305746 65.033481 80.963875 80.963875
19 2560.0 77.649287 70.773218 76.560748 75.851852
20 2688.0 82.463163 75.413632 82.106182 80.880718
21 2816.0 82.602666 73.424595 78.442822 77.330158
22 2944.0 82.784108 72.966370 80.122235 80.122235
23 3072.0 79.638683 74.997490 79.082550 82.903517
24 3200.0 84.099871 78.335374 89.385477 85.333333
25 3328.0 83.226931 77.828428 81.346098 81.530349
26 3456.0 79.351933 75.276907 82.858753 81.435930
27 3584.0 87.466332 81.518940 95.858629 91.470385
28 3712.0 84.230479 79.283603 81.682211 85.455380
29 3840.0 84.421376 79.562590 87.355452 87.562949
30 3968.0 93.006050 86.296981 84.038524 84.504108
31 4096.0 93.662059 87.381330 83.729089 92.119235
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 128.0 0.455111 ... 0.512000 0.512000
1 256.0 2.730667 ... 3.276800 2.978909
2 384.0 7.372800 ... 8.507077 8.507077
3 512.0 14.563555 ... 15.420235 15.420235
4 640.0 22.260869 ... 24.380953 24.380953
5 768.0 32.768000 ... 34.028308 34.028308
6 896.0 39.025776 ... 39.025776 39.025776
7 1024.0 49.932191 ... 52.428801 52.428801
8 1152.0 44.566925 ... 46.656000 45.938215
9 1280.0 51.200001 ... 56.109587 56.109587
10 1408.0 64.138541 ... 65.684049 58.601554
11 1536.0 79.526831 ... 76.106321 75.296679
12 1664.0 63.372618 ... 61.636381 61.636381
13 1792.0 72.983276 ... 68.953520 68.533074
14 1920.0 69.120002 ... 69.467336 69.467336
15 2048.0 73.584279 ... 75.573044 75.234154
16 2176.0 83.155572 ... 79.226957 80.494588
17 2304.0 68.446623 ... 72.387489 72.607513
18 2432.0 71.125224 ... 80.269900 80.963875
19 2560.0 77.649287 ... 76.920185 76.740048
20 2688.0 84.108772 ... 81.053536 83.004501
21 2816.0 79.879498 ... 78.868366 79.011245
22 2944.0 81.698415 ... 77.505492 79.865439
23 3072.0 80.202695 ... 83.886078 83.391907
24 3200.0 82.262212 ... 89.385477 87.074829
25 3328.0 83.226931 ... 86.946008 81.715431
26 3456.0 78.578525 ... 84.420490 84.068369
27 3584.0 87.296493 ... 90.276496 85.064084
28 3712.0 83.386762 ... 83.876864 84.515517
29 3840.0 85.005380 ... 87.701820 87.493673
30 3968.0 92.864488 ... 84.562670 83.807647
31 4096.0 93.596744 ... 83.626378 91.616198
[32 rows x 5 columns]
@@ -409,7 +411,7 @@ We can now compare the performance of our kernel against that of cuBLAS. Here we
.. rst-class:: sphx-glr-timing
**Total running time of the script:** ( 2 minutes 12.630 seconds)
**Total running time of the script:** ( 2 minutes 13.184 seconds)
.. _sphx_glr_download_getting-started_tutorials_03-matrix-multiplication.py:

8
_sources/getting-started/tutorials/sg_execution_times.rst.txt
View File

@@ -5,12 +5,12 @@
Computation times
=================
**03:31.819** total execution time for **getting-started_tutorials** files:
**03:32.367** total execution time for **getting-started_tutorials** files:
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:12.630 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_03-matrix-multiplication.py` (``03-matrix-multiplication.py``) | 02:13.184 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:08.184 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_02-fused-softmax.py` (``02-fused-softmax.py``) | 01:08.183 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:11.005 | 0.0 MB |
| :ref:`sphx_glr_getting-started_tutorials_01-vector-add.py` (``01-vector-add.py``) | 00:10.999 | 0.0 MB |
+---------------------------------------------------------------------------------------------------------+-----------+--------+

19
getting-started/tutorials/01-vector-add.html
View File

@@ -277,8 +277,9 @@ for different problem sizes.</p>
<span class="n">x_vals</span><span class="o">=</span><span class="p">[</span><span class="mi">2</span><span class="o">**</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">12</span><span class="p">,</span> <span class="mi">28</span><span class="p">,</span> <span class="mi">1</span><span class="p">)],</span> <span class="c1"># different possible values for `x_name`</span>
<span class="n">x_log</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="c1"># x axis is logarithmic</span>
<span class="n">line_arg</span><span class="o">=</span><span class="s1">&#39;provider&#39;</span><span class="p">,</span> <span class="c1"># argument name whose value corresponds to a different line in the plot</span>
<span class="n">line_vals</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;torch&#39;</span><span class="p">,</span> <span class="s1">&#39;triton&#39;</span><span class="p">],</span> <span class="c1"># possible values for `line_arg`</span>
<span class="n">line_names</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;Torch&quot;</span><span class="p">,</span> <span class="s2">&quot;Triton&quot;</span><span class="p">],</span> <span class="c1"># label name for the lines</span>
<span class="n">line_vals</span><span class="o">=</span><span class="p">[</span><span class="s1">&#39;triton&#39;</span><span class="p">,</span> <span class="s1">&#39;torch&#39;</span><span class="p">],</span> <span class="c1"># possible values for `line_arg`</span>
<span class="n">line_names</span><span class="o">=</span><span class="p">[</span><span class="s2">&quot;Triton&quot;</span><span class="p">,</span> <span class="s2">&quot;Torch&quot;</span><span class="p">],</span> <span class="c1"># label name for the lines</span>
<span class="n">styles</span><span class="o">=</span><span class="p">[(</span><span class="s1">&#39;blue&#39;</span><span class="p">,</span> <span class="s1">&#39;-&#39;</span><span class="p">),</span> <span class="p">(</span><span class="s1">&#39;green&#39;</span><span class="p">,</span> <span class="s1">&#39;-&#39;</span><span class="p">)],</span> <span class="c1"># line styles</span>
<span class="n">ylabel</span><span class="o">=</span><span class="s2">&quot;GB/s&quot;</span><span class="p">,</span> <span class="c1"># label name for the y-axis</span>
<span class="n">plot_name</span><span class="o">=</span><span class="s2">&quot;vector-add-performance&quot;</span><span class="p">,</span> <span class="c1"># name for the plot. Used also as a file name for saving the plot.</span>
<span class="n">args</span><span class="o">=</span><span class="p">{}</span> <span class="c1"># values for function arguments not in `x_names` and `y_name`</span>
@@ -303,11 +304,11 @@ for different problem sizes.</p>
<img alt="01 vector add" class="sphx-glr-single-img" src="../../_images/sphx_glr_01-vector-add_001.png" />
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>vector-add-performance:
size Torch Triton
0 4096.0 9.600000 9.600000
size Triton Torch
0 4096.0 9.540372 9.600000
1 8192.0 19.200000 19.200000
2 16384.0 38.400001 38.400001
3 32768.0 76.800002 63.999998
2 16384.0 31.999999 31.999999
3 32768.0 63.999998 76.800002
4 65536.0 127.999995 127.999995
5 131072.0 219.428568 219.428568
6 262144.0 341.333321 384.000001
@@ -318,11 +319,11 @@ for different problem sizes.</p>
11 8388608.0 812.429770 812.429770
12 16777216.0 833.084721 833.084721
13 33554432.0 843.811163 843.811163
14 67108864.0 848.362445 849.278610
15 134217728.0 850.656574 851.577704
14 67108864.0 849.278610 848.362445
15 134217728.0 851.577704 850.656574
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 11.005 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 10.999 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-01-vector-add-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/62d97d49a32414049819dd8bb8378080/01-vector-add.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">01-vector-add.py</span></code></a></p>

12
getting-started/tutorials/02-fused-softmax.html
View File

@@ -346,17 +346,17 @@ We will then compare its performance against (1) <code class="code docutils lite
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>softmax-performance:
N Triton Torch (native) Torch (jit)
0 256.0 512.000001 546.133347 273.066674
1 384.0 585.142862 585.142862 267.130429
0 256.0 512.000001 546.133347 264.258068
1 384.0 585.142862 585.142862 261.446801
2 512.0 630.153853 606.814814 264.258068
3 640.0 682.666684 640.000002 269.473696
3 640.0 682.666684 640.000002 265.974036
4 768.0 702.171410 664.216187 273.066663
.. ... ... ... ...
93 12160.0 812.359066 405.755985 329.483481
93 12160.0 812.359066 406.179533 329.483481
94 12288.0 812.429770 415.661740 329.602681
95 12416.0 810.840807 412.149375 329.173158
96 12544.0 810.925276 412.971190 329.292871
97 12672.0 811.007961 412.097543 329.142870
97 12672.0 811.007961 412.097543 329.410251
[98 rows x 4 columns]
</pre></div>
@@ -370,7 +370,7 @@ This means that – when temporary data is too large to fit entirely in the GPU
Note that our Triton kernel is not only faster than PyTorch’s CUDA kernel, it is also <strong>easier to read, understand and maintain</strong>.</p></li>
</ul>
</div></blockquote>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.184 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 1 minutes 8.183 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-02-fused-softmax-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/d91442ac2982c4e0cc3ab0f43534afbc/02-fused-softmax.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">02-fused-softmax.py</span></code></a></p>

70
getting-started/tutorials/03-matrix-multiplication.html
View File

@@ -474,42 +474,44 @@ tensor(True, device=&#39;cuda:0&#39;)
<img alt="03 matrix multiplication" class="sphx-glr-single-img" src="../../_images/sphx_glr_03-matrix-multiplication_001.png" />
<p class="sphx-glr-script-out">Out:</p>
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>matmul-performance:
M cuBLAS cuBLAS (+ torch.nn.LeakyReLU) Triton Triton (+ LeakyReLU)
0 128.0 0.455111 0.372364 0.512000 0.512000
1 256.0 2.978909 2.340571 3.276800 2.978909
2 384.0 7.372800 6.144000 8.507077 8.507077
3 512.0 14.563555 11.915636 16.384000 16.384000
4 640.0 22.260869 18.285714 23.272727 23.272727
5 768.0 32.768000 26.810182 34.028308 34.028308
6 896.0 39.025776 32.672744 39.025776 39.025776
7 1024.0 49.932191 41.943041 52.428801 52.428801
8 1152.0 44.566925 38.779015 46.656000 46.656000
9 1280.0 51.200001 44.521738 56.109587 56.109587
10 1408.0 64.138541 55.068446 65.684049 59.258433
11 1536.0 79.526831 67.408458 75.296679 75.296679
12 1664.0 63.372618 55.893862 61.636381 61.636381
13 1792.0 72.983276 63.860363 68.953520 68.953520
14 1920.0 66.782607 61.168141 68.776119 68.776119
15 2048.0 73.262953 65.793006 75.234154 75.234154
16 2176.0 82.473969 73.712993 79.540109 79.855747
17 2304.0 68.251065 62.207998 73.051599 73.051599
18 2432.0 71.305746 65.033481 80.963875 80.963875
19 2560.0 77.649287 70.773218 76.560748 75.851852
20 2688.0 82.463163 75.413632 82.106182 80.880718
21 2816.0 82.602666 73.424595 78.442822 77.330158
22 2944.0 82.784108 72.966370 80.122235 80.122235
23 3072.0 79.638683 74.997490 79.082550 82.903517
24 3200.0 84.099871 78.335374 89.385477 85.333333
25 3328.0 83.226931 77.828428 81.346098 81.530349
26 3456.0 79.351933 75.276907 82.858753 81.435930
27 3584.0 87.466332 81.518940 95.858629 91.470385
28 3712.0 84.230479 79.283603 81.682211 85.455380
29 3840.0 84.421376 79.562590 87.355452 87.562949
30 3968.0 93.006050 86.296981 84.038524 84.504108
31 4096.0 93.662059 87.381330 83.729089 92.119235
M cuBLAS ... Triton Triton (+ LeakyReLU)
0 128.0 0.455111 ... 0.512000 0.512000
1 256.0 2.730667 ... 3.276800 2.978909
2 384.0 7.372800 ... 8.507077 8.507077
3 512.0 14.563555 ... 15.420235 15.420235
4 640.0 22.260869 ... 24.380953 24.380953
5 768.0 32.768000 ... 34.028308 34.028308
6 896.0 39.025776 ... 39.025776 39.025776
7 1024.0 49.932191 ... 52.428801 52.428801
8 1152.0 44.566925 ... 46.656000 45.938215
9 1280.0 51.200001 ... 56.109587 56.109587
10 1408.0 64.138541 ... 65.684049 58.601554
11 1536.0 79.526831 ... 76.106321 75.296679
12 1664.0 63.372618 ... 61.636381 61.636381
13 1792.0 72.983276 ... 68.953520 68.533074
14 1920.0 69.120002 ... 69.467336 69.467336
15 2048.0 73.584279 ... 75.573044 75.234154
16 2176.0 83.155572 ... 79.226957 80.494588
17 2304.0 68.446623 ... 72.387489 72.607513
18 2432.0 71.125224 ... 80.269900 80.963875
19 2560.0 77.649287 ... 76.920185 76.740048
20 2688.0 84.108772 ... 81.053536 83.004501
21 2816.0 79.879498 ... 78.868366 79.011245
22 2944.0 81.698415 ... 77.505492 79.865439
23 3072.0 80.202695 ... 83.886078 83.391907
24 3200.0 82.262212 ... 89.385477 87.074829
25 3328.0 83.226931 ... 86.946008 81.715431
26 3456.0 78.578525 ... 84.420490 84.068369
27 3584.0 87.296493 ... 90.276496 85.064084
28 3712.0 83.386762 ... 83.876864 84.515517
29 3840.0 85.005380 ... 87.701820 87.493673
30 3968.0 92.864488 ... 84.562670 83.807647
31 4096.0 93.596744 ... 83.626378 91.616198
[32 rows x 5 columns]
</pre></div>
</div>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 12.630 seconds)</p>
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 2 minutes 13.184 seconds)</p>
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-getting-started-tutorials-03-matrix-multiplication-py">
<div class="sphx-glr-download sphx-glr-download-python docutils container">
<p><a class="reference download internal" download="" href="../../_downloads/d5fee5b55a64e47f1b5724ec39adf171/03-matrix-multiplication.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">03-matrix-multiplication.py</span></code></a></p>

8
getting-started/tutorials/sg_execution_times.html
View File

@@ -174,7 +174,7 @@
<div class="section" id="computation-times">
<span id="sphx-glr-getting-started-tutorials-sg-execution-times"></span><h1>Computation times<a class="headerlink" href="#computation-times" title="Permalink to this headline"></a></h1>
<p><strong>03:31.819</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
<p><strong>03:32.367</strong> total execution time for <strong>getting-started_tutorials</strong> files:</p>
<table class="docutils align-default">
<colgroup>
<col style="width: 85%" />
@@ -183,15 +183,15 @@
</colgroup>
<tbody>
<tr class="row-odd"><td><p><a class="reference internal" href="03-matrix-multiplication.html#sphx-glr-getting-started-tutorials-03-matrix-multiplication-py"><span class="std std-ref">Matrix Multiplication</span></a> (<code class="docutils literal notranslate"><span class="pre">03-matrix-multiplication.py</span></code>)</p></td>
<td><p>02:12.630</p></td>
<td><p>02:13.184</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-even"><td><p><a class="reference internal" href="02-fused-softmax.html#sphx-glr-getting-started-tutorials-02-fused-softmax-py"><span class="std std-ref">Fused Softmax</span></a> (<code class="docutils literal notranslate"><span class="pre">02-fused-softmax.py</span></code>)</p></td>
<td><p>01:08.184</p></td>
<td><p>01:08.183</p></td>
<td><p>0.0 MB</p></td>
</tr>
<tr class="row-odd"><td><p><a class="reference internal" href="01-vector-add.html#sphx-glr-getting-started-tutorials-01-vector-add-py"><span class="std std-ref">Vector Addition</span></a> (<code class="docutils literal notranslate"><span class="pre">01-vector-add.py</span></code>)</p></td>
<td><p>00:11.005</p></td>
<td><p>00:10.999</p></td>
<td><p>0.0 MB</p></td>
</tr>
</tbody>

2
searchindex.js
View File

File diff suppressed because one or more lines are too long